© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2914
    Prev
    Next
    INDEX
    Explanations

    string file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    a
    2.74
     fired
    2.28
    क्षिप्त
    2.15
    atrical
    2.13
    ئے
    2.12
    i
    2.11
    ங்கிணை
    2.10
    वेदनशील
    2.09
    ه
    2.06
    ilayer
    2.04
    POSITIVE LOGITS
    먀
    2.88
     рублей
    2.72
    માન્ય
    2.70
    ꒦
    2.60
    即便
    2.58
     ['(?
    2.57
    ❰
    2.53
    ↞
    2.53
    끅
    2.52
    dört
    2.50
    Activations Density 0.040%

    No Known Activations