© 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. 131908
    Prev
    Next
    INDEX
    Explanations

    removal of, when planning, happens in

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

    requires specific following word

    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
    in
    0.52
    ie
    0.48
    it
    0.45
     हवाले
    0.45
    ⇓
    0.44
    leys
    0.42
     Crystall
    0.42
    ere
    0.41
    te
    0.41
    probably
    0.40
    POSITIVE LOGITS
    バッテリー
    0.51
    انے
    0.47
     ተ
    0.47
     পাল্টা
    0.46
     각종
    0.46
     añad
    0.46
    രംഭ
    0.46
     répar
    0.45
     sociedad
    0.44
     válv
    0.44
    Activations Density 0.001%

    No Known Activations