© 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. 175625
    Prev
    Next
    INDEX
    Explanations

    purpose. . benefits

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

    answer each

    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
     дви
    0.45
     XMFLOAT
    0.44
    移
    0.43
     lessened
    0.43
     overruled
    0.42
    }_{[
    0.42
    Digits
    0.41
    StartX
    0.41
     viewers
    0.40
     NZ
    0.40
    POSITIVE LOGITS
     ۲
    0.50
    𒌷
    0.49
    ᱒
    0.49
    ਣ
    0.48
    ждения
    0.48
    IVED
    0.46
     sederhana
    0.45
    afood
    0.45
     ملازمت
    0.44
     dalla
    0.44
    Activations Density 0.001%

    No Known Activations