© 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. 33347
    Prev
    Next
    INDEX
    Explanations

    warranty or condition terms

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

    conditions and requirements

    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
    ༠
    0.49
     hypothes
    0.47
    oursquare
    0.45
    adec
    0.44
    ੦
    0.43
    ene
    0.43
     olmadan
    0.42
    団
    0.42
    edi
    0.42
    Lastly
    0.41
    POSITIVE LOGITS
    m
    0.63
     Face
    0.54
    n
    0.53
    ע
    0.52
     Р
    0.50
     CHANGE
    0.49
     COME
    0.49
     സേ
    0.48
     Proverbs
    0.48
     Ag
    0.48
    Activations Density 0.000%

    No Known Activations