© 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. 189443
    Prev
    Next
    INDEX
    Explanations

    limited selection, selfish ambition

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

    states, relationships, or actions

    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
    高く
    0.52
     ajustes
    0.51
     vocals
    0.49
    ک
    0.47
     в
    0.47
    ेशन
    0.47
    レ
    0.47
     elevados
    0.46
     affirmations
    0.46
     provas
    0.46
    POSITIVE LOGITS
    Sally
    0.46
    രേ
    0.44
     Grizz
    0.43
     Sally
    0.42
    Ő
    0.42
    vare
    0.41
    Scape
    0.41
    ologia
    0.40
     Russel
    0.40
    敀
    0.40
    Activations Density 0.000%

    No Known Activations