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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1011
    Prev
    Next
    INDEX
    Explanations

    using cookies

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

    technical documentation about website cookies and privacy policies, particularly phrases describing how cookies are used and managed.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     same
    -1.57
     to
    -1.56
     только
    -1.51
     что
    -1.36
     همان
    -1.35
    :
    -1.30
    仅
    -1.30
     only
    -1.30
    łaty
    -1.27
    Didn
    -1.19
    POSITIVE LOGITS
     and
    1.37
    娶
    1.19
     chooses
    1.18
     gyerme
    1.17
    כנית
    1.16
     твой
    1.16
    wertes
    1.14
    盅
    1.13
    EACH
    1.13
     данной
    1.13
    Activations Density 0.113%

    No Known Activations