© 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. 8826
    Prev
    Next
    INDEX
    Explanations

    this is a statement about an entity

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

    this followed by description

    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
    চেতন
    0.48
    /
    0.46
    _
    0.45
     substituents
    0.44
    ylmethylsulfanyl
    0.43
    ⟋
    0.43
    /-
    0.42
     delimit
    0.42
     válida
    0.42
    这两个
    0.42
    POSITIVE LOGITS
     is
    0.61
    ра
    0.60
    в
    0.55
    ла
    0.53
    У
    0.52
     isn
    0.51
     particular
    0.50
    Ма
    0.50
    గో
    0.50
    Ли
    0.50
    Activations Density 0.486%

    No Known Activations