© 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-65K
    7. 52337
    Prev
    Next
    INDEX
    Explanations

    tweet numbering or sequence

    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_65k_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
     Rigid
    0.45
    SScript
    0.45
     Waver
    0.44
     Roch
    0.42
    썽
    0.42
    cN
    0.42
     Rene
    0.42
     ST
    0.41
    dim
    0.41
    ুগত্য
    0.41
    POSITIVE LOGITS
    ו
    0.46
    )').
    0.46
     sorrows
    0.45
     preto
    0.44
    ighted
    0.44
     removeFrom
    0.44
    У
    0.43
    вина
    0.42
     finalText
    0.42
    पैकी
    0.42
    Activations Density 0.001%

    No Known Activations