© 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. 224894
    Prev
    Next
    INDEX
    Explanations

    also, about, financial, appearance

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

    risks and consequences

    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
     soldier
    0.54
     إذ
    0.49
     адам
    0.48
     technician
    0.47
    zá
    0.47
    Sha
    0.46
    }+(
    0.46
    }}:
    0.46
    )}.
    0.46
     ham
    0.45
    POSITIVE LOGITS
    گران
    0.49
    绎
    0.48
    也好
    0.45
    釧
    0.45
    łach
    0.43
    ക്ക്
    0.42
     financières
    0.42
     aparecen
    0.42
    ľov
    0.41
    淘宝
    0.41
    Activations Density 0.000%

    No Known Activations