© 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. 81129
    Prev
    Next
    INDEX
    Explanations

    pictures below

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

    not against

    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
    Ofer
    0.45
    危机
    0.44
    दमी
    0.43
    Cpp
    0.43
    佩
    0.42
     nowy
    0.42
    困
    0.42
    一起
    0.42
    DeviceId
    0.42
    ய்டா
    0.42
    POSITIVE LOGITS
    rapes
    0.47
    river
    0.46
    ündung
    0.46
     ಸರಿಯ
    0.44
    గా
    0.44
    werken
    0.43
    rivers
    0.43
    rape
    0.43
    amine
    0.42
    ]";
    0.42
    Activations Density 0.000%

    No Known Activations