© 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. 32027
    Prev
    Next
    INDEX
    Explanations

    Re: subject lines

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

    processes described with subsequent actions

    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
    କୁ
    0.46
    nucleus
    0.46
    圿
    0.46
    ୃ
    0.45
    𝕞
    0.45
    ņ
    0.45
    ém
    0.44
    のか
    0.44
    rf
    0.43
    䞍
    0.43
    POSITIVE LOGITS
     Zuh
    0.45
     manifesto
    0.44
     tenement
    0.44
     councillor
    0.43
     CFO
    0.43
    اتف
    0.43
     lessons
    0.42
     Councillor
    0.42
     Cllr
    0.42
     Talent
    0.41
    Activations Density 0.000%

    No Known Activations