© 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. 94615
    Prev
    Next
    INDEX
    Explanations

    place names and affiliations

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

    potential and income

    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
     abordagem
    0.45
    र्वे
    0.44
     zákon
    0.44
    ẍ
    0.44
     дея
    0.43
     exemplu
    0.43
    薅
    0.42
    ക്കുന്നു
    0.41
     упраж
    0.41
     আইনজীবী
    0.40
    POSITIVE LOGITS
     Satoshi
    0.51
     Survival
    0.47
     Scoop
    0.46
     Turin
    0.46
     Novosibirsk
    0.46
     Novi
    0.45
     Turbulence
    0.45
     Neuroscience
    0.45
     \%
    0.44
     Eindhoven
    0.44
    Activations Density 0.001%

    No Known Activations