© 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. 19536
    Prev
    Next
    INDEX
    Explanations

    You should

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

    grappling hook to swing

    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
    䀎
    0.50
    नाक
    0.46
    䐝
    0.43
     relatos
    0.42
    䚰
    0.41
    শ্ত
    0.41
     asunto
    0.40
    おう
    0.40
     मुसीबत
    0.40
     खासतौर
    0.39
    POSITIVE LOGITS
    _
    0.46
    $
    0.42
    s
    0.42
    а
    0.41
    imgur
    0.40
     سلاټ
    0.40
     OpenAI
    0.40
     Kraków
    0.40
     AI
    0.40
     എന്നാൽ
    0.39
    Activations Density 0.083%

    No Known Activations