© 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. 218952
    Prev
    Next
    INDEX
    Explanations

    specific introductory words

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

    numbers and divisibility checks2. judging situations or actions3. security and peace of mind4. things used 'countless' times

    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
    ्तर
    0.48
    <td>
    0.46
     پیروی
    0.42
     riscos
    0.42
     board
    0.41
    orative
    0.40
    ánt
    0.40
     Micha
    0.40
    aric
    0.40
     કંઈ
    0.39
    POSITIVE LOGITS
     sajana
    0.50
     postavlj
    0.47
     ዋ
    0.45
    ο
    0.44
    e
    0.44
    đe
    0.43
    да
    0.43
    ზი
    0.43
     設定
    0.43
     sporadically
    0.42
    Activations Density 0.000%

    No Known Activations