© 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. 791
    Prev
    Next
    INDEX
    Explanations

    impacts site

    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
    ]
    0.58
     }
    0.53
     叶
    0.50
    ryk
    0.46
    }
    0.46
     তল
    0.45
    umbles
    0.45
    YK
    0.43
     companion
    0.43
    Holder
    0.42
    POSITIVE LOGITS
     શરીર
    0.56
    道の
    0.56
    ς
    0.53
    ્સ
    0.52
     तालुका
    0.52
     나의
    0.51
     स्वरों
    0.51
    стоит
    0.50
     править
    0.49
     வைத்திய
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.