© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151188
    Prev
    Next
    INDEX
    Explanations

    construction, make, use, match

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

    priority and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chwili
    0.57
    纣
    0.43
     stabilizes
    0.43
    crt
    0.43
     સમયે
    0.43
     statt
    0.42
    剩
    0.42
     여기가
    0.42
     plaatsen
    0.41
     ደቂ
    0.41
    POSITIVE LOGITS
    queline
    0.50
    ણામ
    0.49
    ンプー
    0.46
    ಟ
    0.45
     MDR
    0.45
    غیر
    0.44
    anone
    0.43
     Phenomenology
    0.43
     bowing
    0.43
     phenotypic
    0.43
    Activations Density 0.000%

    No Known Activations