© 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. 61579
    Prev
    Next
    INDEX
    Explanations

    ATF SP

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

    things that would compromise

    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
     reparación
    0.51
    적인
    0.46
     rozs
    0.46
     ruptura
    0.45
    햇
    0.45
     laurea
    0.44
     rekan
    0.44
    거운
    0.44
     ala
    0.43
     broker
    0.43
    POSITIVE LOGITS
    JG
    0.43
    }$)
    0.42
     iteratively
    0.42
    SUCCESS
    0.40
     (;
    0.40
    ..</
    0.40
     WD
    0.39
    </div>
    0.39
    Jw
    0.39
    በ
    0.38
    Activations Density 0.000%

    No Known Activations