© 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. 125890
    Prev
    Next
    INDEX
    Explanations

    or both

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

    list options or negations

    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
     convierten
    0.45
    INDUST
    0.44
     টান
    0.43
     textAlign
    0.42
    せ
    0.41
    Ⅸ
    0.41
    ப்பர்
    0.40
     tinggi
    0.40
     μέ
    0.39
    ιώ
    0.39
    POSITIVE LOGITS
     none
    0.61
    none
    0.55
     None
    0.55
    None
    0.54
     NONE
    0.53
     všech
    0.50
    }={\
    0.47
    NONE
    0.45
     جميع
    0.45
     всіх
    0.45
    Activations Density 0.007%

    No Known Activations