© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 489
    Prev
    Next
    INDEX
    Explanations

    what is prompting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isHorizontal
    1.38
    ᅯ
    1.31
    anediyl
    1.30
    ologie
    1.20
    isValue
    1.15
     twos
    1.15
     touchdowns
    1.14
    western
    1.12
    éu
    1.11
    agem
    1.11
    POSITIVE LOGITS
    ↵↵
    1.29
    </tr>
    1.26
    FRAME
    1.22
    鞍
    1.21
    劈
    1.19
     พระ
    1.18
     القر
    1.16
     สัก
    1.13
     매
    1.13
     품
    1.13
    Activations Density 0.001%

    No Known Activations