© 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. 117595
    Prev
    Next
    INDEX
    Explanations

    online now

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

    phrasing is awkward or vague

    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
     रकम
    0.57
    害者
    0.51
     ٹرسٹ
    0.48
     நப
    0.46
     اسک
    0.46
     reaksi
    0.46
    釷
    0.46
    castle
    0.45
    庠
    0.45
    elajaran
    0.45
    POSITIVE LOGITS
    LD
    0.53
    REQ
    0.51
     ș
    0.47
     streamline
    0.47
    CC
    0.47
    Q
    0.46
    LL
    0.46
     monolithic
    0.46
    IT
    0.45
    AA
    0.45
    Activations Density 0.004%

    No Known Activations