© 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. 48520
    Prev
    Next
    INDEX
    Explanations

    incremental benefits

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

    punctuation before instructions

    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
    霰
    0.55
     spiller
    0.54
    icuous
    0.54
     diminuer
    0.53
    iempo
    0.52
    串口
    0.52
    렀
    0.52
    νή
    0.52
     faibles
    0.51
    曛
    0.50
    POSITIVE LOGITS
     of
    0.57
     expertly
    0.49
    data
    0.48
     experts
    0.48
     objectively
    0.46
     data
    0.45
     guided
    0.45
     analyses
    0.45
     intuitively
    0.45
     uniformly
    0.44
    Activations Density 0.000%

    No Known Activations