© 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. 125940
    Prev
    Next
    INDEX
    Explanations

    forward pass

    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
    ७
    0.44
    ૯
    0.43
     äußerst
    0.41
    ྵ
    0.40
    ።
    0.39
    ๒
    0.39
    。
    0.38
    }(\
    0.38
    ९
    0.38
    ⃛
    0.38
    POSITIVE LOGITS
     for
    0.49
     For
    0.42
     tentando
    0.38
     FAQ
    0.37
     defaulted
    0.34
     tenta
    0.34
    つけて
    0.34
     Harvard
    0.34
     George
    0.34
     PDF
    0.34
    Activations Density 0.030%

    No Known Activations