© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 115774
    Prev
    Next
    INDEX
    Explanations

    sewing and crafts

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

    remaining time or progress

    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
     efect
    0.51
     aest
    0.49
     em
    0.48
    蕭
    0.46
    पन
    0.46
     escritos
    0.45
    othelioma
    0.44
    DoS
    0.43
    }'],
    0.43
     envi
    0.43
    POSITIVE LOGITS
     XXII
    0.45
     IX
    0.44
     Oğ
    0.43
     گیرد
    0.43
    ());
    0.42
    ^{-}$
    0.42
    遺跡
    0.42
    礦
    0.41
     കൂടി
    0.41
    嗘
    0.41
    Activations Density 0.000%

    No Known Activations