© 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. 237102
    Prev
    Next
    INDEX
    Explanations

    let alone, his parents, to overestimate

    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
     ü
    0.56
    uts
    0.54
    ues
    0.53
    ig
    0.52
    ola
    0.52
     any
    0.52
     in
    0.51
    ase
    0.51
     transparent
    0.51
    ra
    0.51
    POSITIVE LOGITS
    鶚
    0.48
    ্যাশ
    0.44
     दिखाकर
    0.44
    晏
    0.44
    Cep
    0.43
    시스템
    0.43
     Wasn
    0.43
     અધિકારી
    0.42
     gahet
    0.41
     decoder
    0.41
    Activations Density 0.003%

    No Known Activations