© 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. 155024
    Prev
    Next
    INDEX
    Explanations

    based on or our

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

    actions, states, or entities and their related descriptions

    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
    ລັບ
    0.43
    नाश
    0.41
    ل
    0.40
    য়
    0.39
     controla
    0.38
    ﻟ
    0.38
    メリット
    0.38
    胎
    0.38
    כּ
    0.38
    FA
    0.38
    POSITIVE LOGITS
    ат
    0.51
    besondere
    0.46
     også
    0.46
    varande
    0.45
     także
    0.45
     also
    0.44
     cây
    0.44
    }}{
    0.44
     जीतकर
    0.44
     hatá
    0.44
    Activations Density 0.000%

    No Known Activations