© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79005
    Prev
    Next
    INDEX
    Explanations

    technical terms and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uca
    0.52
    aka
    0.46
    uttab
    0.44
    osch
    0.43
    </em>
    0.42
     ा
    0.42
    agt
    0.42
    गी
    0.42
    oko
    0.41
    up
    0.41
    POSITIVE LOGITS
     comical
    0.48
     hippie
    0.47
     compét
    0.47
    }]$.
    0.46
     murderous
    0.46
     εικό
    0.45
     matières
    0.45
     vele
    0.45
    ר
    0.44
     scattering
    0.44
    Activations Density 0.002%

    No Known Activations