© 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. 69438
    Prev
    Next
    INDEX
    Explanations

    person or thing identification

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

    `guard`, `image`, `target`

    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
    rov
    0.53
    /}
    0.53
    nt
    0.50
    }^
    0.47
    brush
    0.47
    collection
    0.46
    ↵
    0.45
    }
    0.45
    ii
    0.44
    https
    0.44
    POSITIVE LOGITS
    ління
    0.54
    ється
    0.51
    čenja
    0.50
     reproach
    0.49
     colossal
    0.49
     biał
    0.48
     coexist
    0.48
     coaxial
    0.48
     ቢ
    0.47
     substituir
    0.46
    Activations Density 0.000%

    No Known Activations