© 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. 188058
    Prev
    Next
    INDEX
    Explanations

    Copyright, order, place, children

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

    used commercially

    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
    特価
    0.50
    Defocused
    0.49
    ("["
    0.49
    Lapangan
    0.46
    തന്നെ
    0.45
     확인함
    0.45
    ouvement
    0.45
    Schwe
    0.44
    rivial
    0.44
    zeich
    0.44
    POSITIVE LOGITS
    0.60
     올
    0.45
     و
    0.43
     Sienna
    0.42
    颗粒
    0.42
    斷
    0.41
     VIII
    0.40
     It
    0.40
    ويس
    0.39
    圿
    0.39
    Activations Density 0.001%

    No Known Activations