© 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. 55868
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by sentence start

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

    bolded section titles

    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
     zařízení
    0.46
    ﻷ
    0.43
    ені
    0.43
    instellung
    0.43
    শকা
    0.42
     sekä
    0.42
    ﻹ
    0.42
     paradig
    0.42
     termen
    0.41
     indivíduos
    0.41
    POSITIVE LOGITS
    3
    0.41
    ALA
    0.39
    ala
    0.38
    ato
    0.38
    ?’
    0.38
     Blockly
    0.38
     다음과
    0.37
     κ
    0.37
     बहुपद
    0.37
    0.37
    Activations Density 0.000%

    No Known Activations