© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78835
    Prev
    Next
    INDEX
    Explanations

    to connect, curriculum diversity, You need

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ia
    0.48
    daftar
    0.45
     पढ
    0.44
     adjudged
    0.43
    aparte
    0.43
    sequently
    0.43
    jeu
    0.42
    貯
    0.41
     accruing
    0.41
    ன
    0.41
    POSITIVE LOGITS
    多次
    0.48
    观察
    0.43
     to
    0.42
    电路
    0.42
    探测
    0.42
     পুলিশ
    0.41
    溶液
    0.41
     -=
    0.40
    Israel
    0.40
    ानीय
    0.40
    Activations Density 0.005%

    No Known Activations