© 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. 98956
    Prev
    Next
    INDEX
    Explanations

    legal and administrative procedures

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

    the

    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
    oare
    0.55
    in
    0.53
    innt
    0.49
    य़
    0.49
    hil
    0.48
    朓
    0.48
    ა
    0.46
    ਲ
    0.46
    inim
    0.46
    इज
    0.45
    POSITIVE LOGITS
     socialization
    0.52
     administering
    0.48
     اکثر
    0.44
     گ
    0.42
     license
    0.42
     programmer
    0.41
     textual
    0.41
     πλη
    0.40
     acidification
    0.40
     چندین
    0.40
    Activations Density 0.001%

    No Known Activations