© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 5980
    Prev
    Next
    INDEX
    Explanations

    almonds, walnuts, nuts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ться
    1.45
    ו
    1.26
    ка
    1.23
     offrant
    1.23
    करण
    1.20
    ี
    1.20
    CONDITION
    1.20
    ิ
    1.20
     étape
    1.17
     mettant
    1.17
    POSITIVE LOGITS
    sa
    1.30
    েরা
    1.25
    nesses
    1.21
    rous
    1.18
    ness
    1.16
    su
    1.16
    ses
    1.15
                    
    1.14
    ),
    1.13
    е
    1.12
    Activations Density 0.003%

    No Known Activations