© 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. 462
    Prev
    Next
    INDEX
    Explanations

    as "

    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
     along
    1.72
     with
    1.62
     utilising
    1.52
    <bos>
    1.49
     is
    1.49
     of
    1.49
     including
    1.48
    '
    1.43
     and
    1.40
    ’
    1.38
    POSITIVE LOGITS
     fucking
    2.28
     coisas
    2.19
     сути
    2.18
     freaking
    2.17
     lightness
    2.15
     crap
    2.11
     crappy
    2.10
     cortex
    2.09
     shitty
    2.08
     vibe
    2.06
    Activations Density 0.846%

    No Known Activations