© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143084
    Prev
    Next
    INDEX
    Explanations

    traditional comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "):
    0.54
    ia
    0.51
    ay
    0.48
     corro
    0.48
    ana
    0.47
    )?
    0.47
    ra
    0.47
     σ
    0.47
    eas
    0.46
    way
    0.46
    POSITIVE LOGITS
    Vars
    0.49
    Alloc
    0.47
     Aus
    0.46
    ISS
    0.44
    Liz
    0.44
    Aus
    0.44
    RUB
    0.43
     Allocation
    0.43
    Will
    0.42
    DER
    0.42
    Activations Density 0.003%

    No Known Activations