© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42887
    Prev
    Next
    INDEX
    Explanations

    specific blocks

    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
    عهد
    0.47
     improvements
    0.42
    ].
    0.41
     welcoming
    0.40
     improvement
    0.40
     humiliated
    0.40
    .
    0.39
    ).
    0.38
     lamented
    0.38
     retali
    0.38
    POSITIVE LOGITS
    Lik
    0.45
     фаразлау
    0.44
    分隔
    0.43
     टंकी
    0.42
     ክፍ
    0.42
     specifiche
    0.41
     Likely
    0.40
    Cuánto
    0.40
     логи
    0.39
     конкре
    0.39
    Activations Density 0.014%

    No Known Activations