© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3841
    Prev
    Next
    INDEX
    Explanations

    system mountain deeply considerable classic infant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transatlantic
    1.26
    ător
    1.25
     $\%
    1.23
    tevõ
    1.20
    烪
    1.20
    ായിക
    1.19
     harassed
    1.17
    軚
    1.17
    ifaiFace
    1.17
     realizzare
    1.17
    POSITIVE LOGITS
    en
    1.17
    a
    1.16
    it
    1.07
    at
    1.04
    G
    0.99
    V
    0.98
    𝙡
    0.98
    and
    0.97
    C
    0.95
    A
    0.94
    Activations Density 0.000%

    No Known Activations