© 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. 134991
    Prev
    Next
    INDEX
    Explanations

    website or students

    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
    encil
    0.49
    ée
    0.46
    泽
    0.45
    动画
    0.45
    ਯ
    0.44
    μο
    0.44
    兟
    0.44
    idlo
    0.43
     প্রহ
    0.43
     animación
    0.43
    POSITIVE LOGITS
     exacerb
    0.54
     n
    0.53
    ,(
    0.53
     Mö
    0.52
     assesses
    0.52
     setzt
    0.52
     beträgt
    0.51
     immunoprec
    0.51
     ある
    0.50
     shorten
    0.50
    Activations Density 0.000%

    No Known Activations