Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 1453
    Prev
    Next
    INDEX
    Explanations

    easier to understand

    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
     but
    1.80
     But
    1.76
     pure
    1.60
    ↵↵
    1.59
     Can
    1.59
    but
    1.57
    But
    1.51
     things
    1.50
     Summer
    1.50
    .
    1.49
    POSITIVE LOGITS
     namani
    1.15
    кме
    1.14
    ๎
    1.10
    ákat
    1.08
    apayati
    1.06
    apeti
    1.06
     tathapi
    1.05
     vacanam
    1.05
    íte
    1.03
    akaranam
    1.03
    Activations Density 0.008%

    No Known Activations