© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79406
    Prev
    Next
    INDEX
    Explanations

    transitioning concepts and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     esposo
    0.48
     Hardly
    0.44
     Mikhail
    0.42
     indebted
    0.41
     moſt
    0.41
    uji
    0.41
    怨
    0.40
     Ira
    0.40
    _:
    0.40
     awoke
    0.40
    POSITIVE LOGITS
     diret
    0.43
    childNodes
    0.42
     ratchet
    0.41
    JF
    0.41
    ᠰ
    0.41
     semaphore
    0.40
     PNP
    0.40
     be
    0.40
    ois
    0.40
    verters
    0.40
    Activations Density 0.002%

    No Known Activations