© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2148
    Prev
    Next
    INDEX
    Explanations

    limiting instructions

    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_16_width_65k_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
     be
    1.26
     in
    1.16
     cliques
    1.13
    ר
    1.10
    ről
    1.06
     endeav
    1.04
     extrapolate
    0.99
    ۔
    0.96
     strides
    0.96
     merr
    0.95
    POSITIVE LOGITS
    ма
    1.09
    ш
    1.06
    as
    1.02
    ่า
    0.98
    ิ
    0.97
    ent
    0.95
    <0x80>
    0.93
    1
    0.93
    6
    0.93
    ız
    0.87
    Activations Density 0.570%

    No Known Activations