© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4204
    Prev
    Next
    INDEX
    Explanations

    get in shape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
    埆
    1.15
    ErrorClazz
    1.14
    Ꮬ
    1.14
    𒈾
    1.13
    𒀪
    1.11
    <unused847>
    1.11
    𒄿
    1.10
    𒀹
    1.10
    𒀝
    1.10
    ்ட்டெமி
    1.09
    POSITIVE LOGITS
     *
    0.63
     or
    0.56
     саме
    0.55
    一
    0.53
     A
    0.52
     One
    0.52
     …
    0.51
     vs
    0.51
     fact
    0.49
     car
    0.49
    Activations Density 0.000%

    No Known Activations