© 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. 180895
    Prev
    Next
    INDEX
    Explanations

    press release wire

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

    evolution, choose, path

    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
    坎
    0.51
    ItemBackground
    0.40
    FLICT
    0.40
    RangeException
    0.40
    WinCounter
    0.39
    좇
    0.39
    顏
    0.38
    地产
    0.38
    InputField
    0.38
    Ligações
    0.38
    POSITIVE LOGITS
     enkele
    0.51
     killers
    0.50
     入り
    0.47
     Surprisingly
    0.47
     EVERY
    0.47
     ફરી
    0.46
     কেনো
    0.46
     kembali
    0.45
     Gossip
    0.45
     દરેક
    0.44
    Activations Density 0.000%

    No Known Activations