© 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. 53207
    Prev
    Next
    INDEX
    Explanations

    Rationale, Mobile, Blaze, beauty, Terms

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

    repeating patterns in strings

    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
    .=
    0.47
    ⇆
    0.45
    스러운
    0.45
     καλύτε
    0.44
     prête
    0.43
    場合
    0.42
    塭
    0.42
    م
    0.41
     Acción
    0.41
    ก
    0.41
    POSITIVE LOGITS
    lucent
    0.42
    ோடு
    0.39
     curiously
    0.39
     dobu
    0.39
     chronic
    0.38
    blower
    0.38
     viscosity
    0.38
    opaque
    0.36
     membuatnya
    0.36
     resistivity
    0.36
    Activations Density 0.000%

    No Known Activations