© 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. 80233
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs

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

    absorb energy

    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
     يَ
    0.53
    ять
    0.52
    ي
    0.48
    '=
    0.47
    راهيم
    0.46
    йон
    0.46
     يه
    0.45
     سلامه
    0.44
    ем
    0.44
     رسمي
    0.44
    POSITIVE LOGITS
     aval
    0.50
     as
    0.47
     aven
    0.46
     Sets
    0.45
     with
    0.45
     ●
    0.45
    ranges
    0.44
     Abre
    0.44
     when
    0.43
    txt
    0.43
    Activations Density 0.001%

    No Known Activations