© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5391
    Prev
    Next
    INDEX
    Explanations

    PDDL, PDB, Dungeons

    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
     shy
    0.45
     sp
    0.44
     squir
    0.43
     exc
    0.43
     g
    0.42
    spapers
    0.40
     pick
    0.40
     dev
    0.40
     sl
    0.40
     damp
    0.40
    POSITIVE LOGITS
    İ
    0.75
    Ö
    0.69
    Ü
    0.67
    UCK
    0.66
    Ş
    0.64
    ITE
    0.64
    IK
    0.63
    IZ
    0.63
    ITS
    0.63
    UE
    0.63
    Activations Density 0.472%

    No Known Activations