© 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. 43992
    Prev
    Next
    INDEX
    Explanations

    test of, to install

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

    bend others to their will

    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
     Хоро
    0.49
     Galatasaray
    0.49
     Alhaji
    0.49
     Ismail
    0.45
     %).
    0.45
     Berlusconi
    0.43
     वारदात
    0.43
     รอ
    0.42
     Rodr
    0.42
     राह
    0.41
    POSITIVE LOGITS
    ክ
    0.42
    UID
    0.41
     menghub
    0.41
    雄
    0.39
     unchanging
    0.39
    டனும்
    0.39
    性和
    0.38
    りが
    0.38
     способности
    0.38
     merken
    0.38
    Activations Density 0.000%

    No Known Activations