© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 537
    Prev
    Next
    INDEX
    Explanations

    items with features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    сро
    2.30
    ouncement
    2.27
    ματο
    2.25
    鳅
    2.08
    phasis
    2.04
    сле
    2.03
     organisation
    2.02
    organiser
    2.02
    ungannya
    2.01
     rém
    2.00
    POSITIVE LOGITS
    7
    2.35
    8
    2.34
    6
    2.26
    0
    2.17
    9
    1.96
    5
    1.94
    4
    1.92
    rinsic
    1.68
    º
    1.58
    3
    1.54
    Activations Density 0.898%

    No Known Activations