© 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. 1195
    Prev
    Next
    INDEX
    Explanations

    parameters and episodes

    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
     plagues
    2.20
    挈
    2.15
    ensitive
    2.12
    埗
    2.10
    ubwa
    2.09
    )}=\
    2.07
    pero
    2.06
     nyingi
    2.06
     flashbacks
    2.05
    kwik
    2.02
    POSITIVE LOGITS
    formed
    1.55
    being
    1.35
    0
    1.33
     deserved
    1.28
    deserved
    1.26
    örd
    1.24
    ОВО
    1.18
    knowing
    1.16
    -
    1.15
    4
    1.13
    Activations Density 0.087%

    No Known Activations