© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113541
    Prev
    Next
    INDEX
    Explanations

    V chain identifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    programming-related variables and technical abbreviations, particularly focusing on identifiers like 'v', 'var', 'vptr', and 'vec' in code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    神
    -2.61
     thee
    -2.58
    頽
    -2.55
     WHICH
    -2.45
     ―
    -2.38
     ‘‘
    -2.34
     uuidv
    -2.31
    ⽼
    -2.30
    韪
    -2.28
     ""}
    -2.25
    POSITIVE LOGITS
     "
    2.58
     These
    2.45
    </h3>
    2.45
    It
    2.42
    If
    2.41
     It
    2.31
    ':
    2.27
    </strong>
    2.22
     зима
    2.19
     Architekten
    2.19
    Activations Density 1.467%

    No Known Activations