© 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-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 1716
    Prev
    Next
    INDEX
    Explanations

    AI, code, website, person, emoji

    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
     (’
    3.12
    ………….
    3.04
    …………………………………………
    2.91
    …………..
    2.86
    (“
    2.84
    ……….
    2.81
    ………..
    2.78
    ﹐
    2.71
     ………………………………..
    2.68
     (‘
    2.67
    POSITIVE LOGITS
    7
    3.47
    8
    3.39
    6
    3.21
    9
    3.03
    4
    2.94
    3
    2.94
    5
    2.88
    2
    2.27
    0
    2.25
    1
    1.92
    Activations Density 0.072%

    No Known Activations