© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8977
    Prev
    Next
    INDEX
    Explanations

    follow or behind

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

    following or preceded by

    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_40_width_16k_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
    iquity
    0.35
    leftrightarrow
    0.35
    হত্যা
    0.33
    rants
    0.32
    grond
    0.32
    icate
    0.32
    MSFontService
    0.32
    ڦ
    0.32
    obje
    0.31
    llbracket
    0.31
    POSITIVE LOGITS
     Follow
    2.72
     follow
    2.66
     behind
    2.61
    Follow
    2.59
     FOLLOW
    2.58
    follow
    2.50
     followed
    2.44
     Behind
    2.44
    behind
    2.42
    Behind
    2.41
    Activations Density 0.593%

    No Known Activations