© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2480
    Prev
    Next
    INDEX
    Explanations

    titles and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ULATIONS
    2.12
     Fixed
    2.10
    گاہ
    2.06
     Decision
    2.04
    fixed
    2.02
    Descending
    1.99
    dang
    1.99
    ﻃ
    1.96
    starts
    1.93
    きの
    1.91
    POSITIVE LOGITS
    л
    3.54
     MongoClient
    2.88
    chap
    2.66
    oluene
    2.64
    asie
    2.63
    iop
    2.60
    lemy
    2.58
    ospor
    2.55
    qar
    2.50
    ి
    2.47
    Activations Density 0.022%

    No Known Activations